Related papers: Dynamic Risk Assessments for Offensive Cybersecuri…

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

Cyber risk assessment is a fundamental activity for enhancing the protection of an organization, identifying and evaluating the exposure to cyber threats. Currently, this activity is carried out mainly manually and the identification and…

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…

In a world of ever-increasing systems interdependence, effective cybersecurity policy design seems to be one of the most critically understudied elements of our national security strategy. Enterprise cyber technologies are often implemented…

In the vast domain of cybersecurity, the transition from reactive defense to offensive has become critical in protecting digital infrastructures. This paper explores the integration of Artificial Intelligence (AI) into offensive…

Traditional static cybersecurity models often struggle with scalability, real-time detection, and contextual responsiveness in the current digital product ecosystems which include cloud services, application programming interfaces (APIs),…

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…

Frontier artificial intelligence (AI) systems pose increasing risks to society, making it essential for developers to provide assurances about their safety. One approach to offering such assurances is through a safety case: a structured,…

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

This, with the ever-increasing sophistication of cyberwar, calls for novel solutions. In this regard, Large Language Models (LLMs) have emerged as a highly promising tool for defensive and offensive cybersecurity-related strategies. While…

When undertaking cyber security risk assessments, we must assign numeric values to metrics to compute the final expected loss that represents the risk that an organization is exposed to due to cyber threats. Even if risk assessment is…

Cybersecurity spans multiple interconnected domains, complicating the development of meaningful, labor-relevant benchmarks. Existing benchmarks assess isolated skills rather than integrated performance. We find that pre-trained knowledge of…

In the face of evolving cyber threats such as malware, ransomware and phishing, autonomous cybersecurity defense (ACD) systems have become essential for real-time threat detection and response with optional human intervention. However,…

Given the increase in cybercrime, cybersecurity analysts (i.e. Defenders) are in high demand. Defenders must monitor an organization's network to evaluate threats and potential breaches into the network. Adversary simulation is commonly…

Autonomous agents are increasingly deployed in both offensive and defensive cyber operations, creating high-speed, closed-loop interactions in critical infrastructure environments. Advanced Persistent Threat (APT) actors exploit "Living off…

Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and…

Frontier AI developers operate at the intersection of rapid technical progress, extreme risk exposure, and growing regulatory scrutiny. While a range of external evaluations and safety frameworks have emerged, comparatively little attention…

Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI…

Large Language Model (LLM) agents are increasingly proposed to automate offensive security tasks, with recent studies reporting near human-level success rates in Capture-the-Flag (CTF) challenges. We here revisit these results, providing a…

Rooted in collaborative efforts, cybersecurity spans the scope of cyber competitions and warfare. Despite extensive research into team strategy in sports and project management, empirical study in cyber-security is minimal. This gap…